Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx agentmods add commands/doncheli/don-cheli-sdd/buclegit clone --depth 1 https://github.com/doncheli/don-cheli-sddWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/commands/doncheli/don-cheli-sdd/bucle)<a href="https://agentmods.dev/commands/doncheli/don-cheli-sdd/bucle"><img src="https://agentmods.dev/badge/commands/doncheli/don-cheli-sdd/bucle.svg" alt="Measured on agentmods" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5 | $0.00013 | $0.00523 |
| Opus 5 | $0.00006 | $0.00262 |
| Sonnet 5 | $0.00003 | $0.00105 |
| Haiku 4.5 | $0.00001 | $0.00052 |
Grade A, and why
bucle scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured yesterday.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
What it actually says
/bucle
Objetivo
Lanzar el bucle autónomo que ejecuta las historias de usuario una por una hasta completar o agotar iteraciones.
Uso
/bucle [max_iteraciones]
max_iteraciones: Número máximo de iteraciones (default: 10)
Prerrequisitos
- Archivo
.dc/sesion/prd.jsonexistente - Al menos una historia con
pasa: false
Comportamiento
- Verificar que prd.json existe
- Contar historias restantes
- Lanzar el script
bucle.sh - Para cada iteración:
- Seleccionar historia prioritaria no completada
- Ejecutar en contexto fresco (aislado)
- Verificar criterios de aceptación
- Actualizar prd.json
- Registrar en progreso.md
- Terminar cuando:
- Todas las historias pasan →
COMPLETO - Máximo iteraciones alcanzado → fallo
- Historia bloqueada 2 veces → saltar y continuar
- Todas las historias pasan →
Output
=== Bucle Don Cheli Iniciado ===
Historias: 5 pendientes, 0 completadas
Máximo iteraciones: 10
--- Iteración 1/10 ---
Historia: HU-001 [P1] Estructura de archivos
Estado: PASÓ ✅
--- Iteración 2/10 ---
Historia: HU-002 [P2] Comando historias-generar
Estado: PASÓ ✅
...
=== COMPLETO ===
Las 5 historias pasaron en 5 iteraciones.
Ver progreso: .dc/progreso.md
Gestión de Errores
| Situación | Comportamiento |
|---|---|
| prd.json faltante | Error + sugerir /historias-generar |
| Sin historias pendientes | Mensaje "Nada que hacer" |
| Historia falla 1x | Reintentar en siguiente iteración |
| Historia falla 2x | Saltar + registrar |
| Máximo iteraciones | Salir con mensaje |
Contexto Fresco
Cada historia se ejecuta en su propio contexto aislado. El agente NO acumula confusión de sesiones anteriores. Investigaciones muestran que las respuestas de LLM degradan notablemente en contextos largos. Contexto fresco = agente más inteligente.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- yesterday First seen · 75 lines · 13 tokens per session scan A 00bd98f13678
bucle is a command published in the GitHub repository doncheli/don-cheli-sdd (57 stars, last pushed 25d ago), licensed Apache-2.0. It adds 13 tokens to every session and 523 once invoked, about $0.0001 per session on Opus 5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-09-03.
Other commands, from other repositories
add-phase
Add phase to end of current milestone in roadmap.
insert-phase
Insert urgent work as decimal phase (e.g., 72.1) between existing phases.
reapply-patches
Reapply local modifications after a PBR update.
remove-phase
Remove a future phase from roadmap and renumber subsequent phases.
research-phase
Research how to implement a phase (standalone — usually use /pbr:plan-phase instead).
update
Update PBR to latest version with changelog display.